GT 280/260 performance comparison to 3870X2

http://resources.vr-zone.com//newspi...erformance.jpg

Quote:

---

CJ sent us a performance chart comparing Radeon HD 3870 X2 against the GeForce GTX 280 and GTX 260 on some of the games out there. Although, the benchmarks are done internally by Nvidia but it is probably conclusive to compare GTX 280 and GTX 260 here. The drivers for GeForce GTX 200 cards is the upcoming GeForce Release 177 while the drivers for 3870 X2 is a rather old Catalyst 8.3.

---

http://www.vr-zone.com/articles/GeFo...ance/5817.html

The GT200 are basically kicking the crap out of 3870X2, but not as much as some people on this forum think.

Now, we need some 4870 & 4870X2 benches.

EDIT: Because the chart on the slide is misleading I made another one where the performance ratio is represented in proportion:
http://img88.imageshack.us/img88/172...benchesvk3.jpg

how is this news its got no info on specs or settings and has no actual numbers as well as being out of proportion

Insane! Crazy Performance, can't wait to see it in action.

already posted in the 9900GTX & GTS thread in sticky - http://www.xtremesystems.org/forums/...185628&page=35

Thanks for correcting the misleading chart. The GTX260 looks quite attractive.

Quote:

---

Originally Posted by revogamer

already posted in the 9900GTX & GTS thread in sticky - http://www.xtremesystems.org/forums/...185628&page=35

---

That doesnt mean its not welcome here. I dont read that whole thread.

This has been posted in both the threads

Seriously, please read those threads before you post "new" news

PS - Cat 8.3? Lol

just shows how much faster thay are to what the 3870x2 Was not to it is now, add bars for a 3870x2 w/8.5 and 8.6beta then see if it looks so good for the 260

Quote:

---

Originally Posted by v0dka

Thanks for correcting the misleading chart. The GTX260 looks quite attractive.



That doesnt mean its not welcome here. I dont read that whole thread.

---

We don't need another thread.

Why do they bother w/ numbers? What about a big ball. It could be green...the other would be red and not quite as large. Then if they really needed numbers and random letters, it could be dipped in honey and thrown into a scrabble pit.

So this thing will not destroy my PSU, right? Gotta love a hot summer followed by a hot video card to screw w/ my cooling and OC. :D

Catalyst 8.3.
*facepalm*

This is a completely, totally and utterly useless chart, no matter how one corrects the proportions.

Quote:

---

Originally Posted by largon

Catalyst 8.3.
*facepalm*

This is a completely, totally and utterly useless chart, no matter how one corrects the proportions.

---

QFT.

You may close this thread :D:D:D

Lol, Nvidia desperately fighting ATI's OLD GEN hardware and they need to show ATI's results with 3 months old drivers to make their new product look good! :ROTF:

Quote:

---

Originally Posted by Calmatory

Lol, Nvidia desperately fighting ATI's OLD GEN hardware and they need to show ATI's results with 3 months old drivers to make their new product look good! :ROTF:

---

If ATIs HD3870X2 is old gen, it should have good drivers 3 months ago, no???

I wouldn't call it old gen, because you only got good drivers about 2 months ago, not that long to consider a product old gen, is it?

And I don't think this is a desperate act, is just BS marketing.

Looks like 2008 will be another year with complete nVidia dominance.

Quote:

---

Originally Posted by Shintai

Looks like 2008 will be another year with complete nVidia dominance.

---

performance wise for sure, but i think the price/performance battle will get very interesting.

still waiting on 4800's performance, but have a feeling the G280 will come out a bit above..ATI should just give up soon if this is the case..

G260 look's like a nice card for my needs

Quote:

---

Originally Posted by strange|ife

still waiting on 4800's performance, but have a feeling the G280 will come out a bit above..ATI should just give up soon if this is the case..

G260 look's like a nice card for my needs

---

nvidia is just crazy enough to produce such an enormous chip... (in size, i dont know anbout performance)
ATI/AMD is all about price/performance lately, they dont seem to care much about the enthusiast market

Quote:

---

Originally Posted by Calmatory

Lol, Nvidia desperately fighting ATI's OLD GEN hardware and they need to show ATI's results with 3 months old drivers to make their new product look good! :ROTF:

---

:hehe:

yeah; but at least they have shown a result vs. ati ...*crickets*...

Quote:

---

Originally Posted by Shintai

Looks like 2008 will be another year with complete nVidia dominance.

---

actually I would expect you to comment on this with: larabee will have total dominance by end 2008 :rofl:

but your current comment is already one to "complete" remember :ROTF:

btw redesigned chart looks provides much better information

Thanks for the post gO.

Don't blame the messenger people. Gojdo is just trying to help spread the word.

Perkam

thanks for the new chart , it doesnt skew things as much :D good work

Quote:

---

Originally Posted by adamsleath

:hehe:

yeah; but at least they have shown a result vs. ati ...*crickets*...

---

:rofl: Crickets! :ROTF::ROTF:

It is somewhat misleading. IF the 4870x2 is twice as fast as the 3870x2 it would win half of those tests and the GTX'es would only have solid wins in two.

Quote:

---

Originally Posted by lapdog

It is somewhat misleading. IF the 4870x2 is twice as fast as the 3870x2 it would win half of those tests and the GTX'es would only have solid wins in two.

---

The 4870 is not twice as fast as the 3870 so the 4870X2 will definitely not be twice as fast as a 3870X2.

In fact, early drivers for the 4870X2 (which is July we're talking about btw) will most likely have minor scaling issues just as the 3870X2 did, it will have a smaller performance delta than the 4870 vs the 3870.

The 4870 AT MOST (with huge amounts of wishful thinking) will only be about 50% faster than the 3870 in games and real world applications. It will be a lot faster in benchmarks but I don't "play" benchies,:cool:

LMAO ! Nvidia guy who did this first chart should go to primary school to learn some math, what a misleading marketing.Shame on you,nvidia.

Quote:

---

Originally Posted by perkam

The 4870 is not twice as fast as the 3870 so the 4870X2 will definitely not be twice as fast as a 3870X2.

In fact, early drivers for the 4870X2 (which is July we're talking about btw) will most likely have minor scaling issues just as the 3870X2 did, it will have a smaller performance delta than the 4870 vs the 3870.

The 4870 AT MOST (with huge amounts of wishful thinking) will only be about 50% faster than the 3870 in games and real world applications. It will be a lot faster in benchmarks but I don't "play" benchies,:cool:

---

finally another has seen the light!!! like i have said before the 4870 is not going to be to much faster than the 9800gtx and that will put the 4870x2 a little faster than the 9800gx2 so now it's AMD's new gen competing with nvidia's "old gen". but one thing i for see in both cards is new drivers will make a large performance increase as time passes on.

Quote:

---

Originally Posted by Pinacolada

LMAO ! Nvidia guy who did this first chart should go to primary school to learn some math, what a misleading marketing.Shame on you,nvidia.

---

"Misleading marketing" is a bit of misnoma, no?

Marketing is intended to be misleading, why would nVidia produce a slide that showed a 'fair' comparison with a smaller gap? Would more people buy it because they're being underwhelmingly honest? No.

I'm not defending their flagrantly biased use of scale, lack of numbers, or test scenario detail to back up the data, but this is exactly how the marketing departments of BOTH companies work. Unfortunately there are n00bs who will believe this graph.

Likewise, there are some who will believe the 'normalized' graph that someone produced in the HD4000/GTX280 threads that plotted a 65% increase across the board for the 4870 card. That, was equally as misleading.

Suck it all up and come to your own conclusions. Trust those websites who will be open and honest with the settings, scale and provide proof. :up:

Quote:

---

Originally Posted by r1ch

"Misleading marketing" is a bit of misnoma, no?

Marketing is intended to be misleading, why would nVidia produce a slide that showed a 'fair' comparison with a smaller gap? Would more people buy it because they're being underwhelmingly honest? No.

I'm not defending their flagrantly biased use of scale, lack of numbers, or test scenario detail to back up the data, but this is exactly how the marketing departments of BOTH companies work. Unfortunately there are n00bs who will believe this graph.

Likewise, there are some who will believe the 'normalized' graph that someone produced in the HD4000/GTX280 threads that plotted a 65% increase across the board for the 4870 card. That, was equally as misleading.

Suck it all up and come to your own conclusions. Trust those websites who will be open and honest with the settings, scale and provide proof. :up:

---

This is not correct. Marketing primary goal is to bring public awareness to what is available for sale. Not to mislead the public :rolleyes:

that would be propaganda ?

nv marketing primary goal is to make the GTX Titanic look good

Quote:

---

Originally Posted by bill_d

nv marketing primary goal is to make the GTX Titanic look good

---

They dont need marketing for that.

Quote:

---

Originally Posted by Eastcoasthandle

This is not correct. Marketing primary goal is to bring public awareness to what is available for sale. Not to mislead the public :rolleyes:

---

Exactly. If they'd produced the graph with a true scale then it wouldn't have caught so many people's eyes. We wouldn't be talking about it, and it wouldn't have it's own thread. In that respect, job done for nVidia.

Tbh, the only people who are being mislead are those who are dumb enough not to realise the scale (not to mention trusting a biased source).

Do you people think that CrossFire-X HD 4870X2 will beat a GTX 280?

Quote:

---

Originally Posted by Isaac MM

Do you people think that CrossFire-X HD 4870X2 will beat a GTX 280?

---

Even a single HD4870X2 could beat a GTX280 (or not), just wait for the truth instead of feeding yourself with fantasy ;)

Quote:

---

Originally Posted by Isaac MM

Do you people think that CrossFire-X HD 4870X2 will beat a GTX 280?

---

There is a definite possibility that it can beat it(from game to game since cards/GPUs act differently over the range of game engines).
IF 4870 is indeed 40% faster than 9800GTX,then 4870X2 will be around 40%(or some less) faster than 9800GX2 which is in line with GTX280 performance expectations(around 30% faster than 9800GX2).

can someone just press the fastward button till august:D

Quote:

---

Originally Posted by bill_d

can someone just press the fastward button till august:D

---

QFT :D

I am still waiting for a true, up-front comparison before I make any descisions, or claims for that matter. All that I know, is that 2008/2009 is going to be really fun! :D

3x GTX 280 vs. 2x HD4870X2.

Quote:

---

...though, the benchmarks are done internally by Nvidia....

---

nuff said...... BS, will wait for some real numbers.

Quote:

---

Originally Posted by Calmatory

3x GTX 280 vs. 2x HD4870X2.

---

That's what I'm talkin' about.

Quote:

---

Originally Posted by revogamer

already posted in the 9900GTX & GTS thread in sticky - http://www.xtremesystems.org/forums/...185628&page=35

---

First, thanks for fixing that badly skewed chart. Typical marketing mumbo jumbo.
As for posting in the other thread, the new cards are not named 9900GTX & GTS, so maybe that thread should die off.

Before people here starts ooh-ing and aah-ing over those scores they should look at the little green logo in the top right corner and consider the following:

1. Would Nvidia include games that favor ATI in those slides?
2. Would Nvidia use settings that favor ATI cards?
3. Would Nvidia use drivers that favor ATI cards?
4. Would Nvidia present these data in a favorable way to ATI?

If you've answered yes to any of those questions I urge you to have another long look at that little green logo and consider the source. While I do not doubt that the GTX's will kill the 3870X2 these data cannot/must not/should not be taken at face value.

FWIW the 3870X2 might actually beat the GTX 280 in WIC as there is a 2,6X speed-up in going from Cat 8.3 to 8.4:
http://images.tweaktown.com/imagebank/cat84_g_11.gif
[source]

this looks like an fps chart for GFX cards from 1983, does anyone know what in the hell this chart means or even represents besides the "we are better than them" theory. Someone needs to let Nvidia know that only Albert Einstein and Isaac Newton are allowed to show us charts that we dont understand!

Quote:

---

Originally Posted by Boissez

Before people here starts ooh-ing and aah-ing over those scores they should look at the little green logo in the top right corner and consider the following:

1. Would Nvidia include games that favor ATI in those slides?
2. Would Nvidia use settings that favor ATI cards?
3. Would Nvidia use drivers that favor ATI cards?
4. Would Nvidia present these data in a favorable way to ATI?

If you've answered yes to any of those questions I urge you to have another long look at that little green logo and consider the source. While I do not doubt that the GTX's will kill the 3870X2 these data cannot/must not/should not be taken at face value.

FWIW the 3870X2 might actually beat the GTX 280 in WIC as there is a 2,6X speed-up in going from Cat 8.3 to 8.4:
http://images.tweaktown.com/imagebank/cat84_g_11.gif
[source]

---

This ruined a perfectly sarcastic-unbiased post :)

Quote:

---

Originally Posted by Mr.Guvernment

nuff said...... BS, will wait for some real numbers.

---

Quote:

---

Originally Posted by Boissez

Before people here starts ooh-ing and aah-ing over those scores they should look at the little green logo in the top right corner and consider the following:

1. Would Nvidia include games that favor ATI in those slides?
2. Would Nvidia use settings that favor ATI cards?
3. Would Nvidia use drivers that favor ATI cards?
4. Would Nvidia present these data in a favorable way to ATI?

If you've answered yes to any of those questions I urge you to have another long look at that little green logo and consider the source. While I do not doubt that the GTX's will kill the 3870X2 these data cannot/must not/should not be taken at face value.

FWIW the 3870X2 might actually beat the GTX 280 in WIC as there is a 2,6X speed-up in going from Cat 8.3 to 8.4:
http://images.tweaktown.com/imagebank/cat84_g_11.gif
[source]

---

exactly..... logo = charts means nothing

1) I agree with many posters here. Shame on nVidia, they should give a credit to AMD for the chart style :)
2) We have no info about the hardware, the OS(es) and the software used. Also we have no info about the resolutions used in that comparison. So we can safely assume that the chart is representing the best case for the nVidia cards and/or the worst case for the 3870X2.
3) nVidia used outdated and unoptimized ATi drivers, while they haven't specified the drivers for their new cards. nVidia was cheating in the past and we don't know if they are not going to do the same again with the drivers for their new cards.

The chart only gives a simple image about the performance of GT200 in the best case. This month we'll see a lot of benches done by the lucky individuals who have connections with nVidia.

Quote:

---

Originally Posted by Calmatory

3x GTX 280 vs. 2x HD4870X2.

---

In performance, 3x GTX 280.
In price/performance, probably 2x HD 4870X2.

Why should 4870 be only %50 (and even that "with a lot of wishful thinking") faster than 3870 when its processing power doubled, memory bandwidth doubled, memory amount doubled, texture addressing/filtering more than doubled, and z-fillrate at least doubled?

And if 4870 is %50 better than 3870, which makes 4850 only %10 or 15 better than 3870; how the hell can AMD/ATi justify 4850's price of $220, whereas HD3870's are as low as $150?

I would expect 4870 to be close to twice 3870, which would justify both part's prices and specifications.

Quote:

---

Originally Posted by annihilat0r

Why should 4870 be only %50 (and even that "with a lot of wishful thinking") faster than 3870 when its processing power doubled, memory bandwidth doubled, memory amount doubled, texture addressing/filtering more than doubled, and z-fillrate at least doubled?

And if 4870 is %50 better than 3870, which makes 4850 only %10 or 15 better than 3870; how the hell can AMD/ATi justify 4850's price of $220, whereas HD3870's are as low as $150?

I would expect 4870 to be close to twice 3870, which would justify both part's prices and specifications.

---

Shaders aint double, ROPs aint changed at all and so on and on.

There are 50% shaders, but at 35% higher clock. So you might consider them doubled (1.5 * 1.35 = 2). There are same nubmer of ROPs as on 3870 but their frequency is being raised for 35%. The number of texturing units has been doubled and their frequency raised for 35% or x2.7 more texturing capabilities compared to 3870. Don't underestimate the 4870. IMO it will be at least 50% faster then 3870.

Quote:

---

Originally Posted by gOJDO

There are 50% shaders, but at 35% higher clock. So you might consider them doubled (1.5 * 1.35 = 2). There are same nubmer of ROPs as on 3870 but their frequency is being raised for 35%. The number of texturing units has been doubled and their frequency raised for 35% or x2.7 more texturing capabilities compared to 3870. Don't underestimate the 4870. IMO it will be at least 50% faster then 3870.

---

Sure about all those clock raises and shaderspeeds?

When looking at the 4850 vs 3850 it doesnt seem to be so.

http://resources.vr-zone.com//newspi...03/RV770-6.png

Memory is also a good 150Mhz lower than the rumour said.

Plus the core speed is 43Mhz lower than on HD3850 aint it?

And even on HD3870 vs HD4870 (If we trust the rumours) its abit udner 10% core speed increase. Not sure where you get those 35% from besides the shaderpart only. TMUs etc aint affected.

Shaders haven't doubled and I didn't imply they did; but with increasing clock rates, math processing power has doubled. Z-fill per clock has either doubled or quintupled, I'm not sure; and as gojdo pointed out, the main bottleneck for R600-based cards, texture management rate, has nearly tripled (although I'm not sure on the clock rate, for the core except shaders is it really %35? I thought it was just 800 or 900MHz); and counting double the memory bandwidth and memory amount, nearly everything you can imagine has at least doubled.

The performance has to be somewhere close to double 3870. If it's only 1.5x, HD4850's price of $220 doesn't make any sense at all against the $150 HD3870. To me, everything points to the direction that 4870 will at least be 1.7 or 1.8 times HD3870, and 4850 will be at least 1.4-1.5 times HD3870, which fits in the 3dmark Vantage performance scores we have heard (4850 being slightly faster than 9800GTX)

Quote:

---

Originally Posted by annihilat0r

Shaders haven't doubled and I didn't imply they did; but with increasing clock rates, math processing power has doubled. Z-fill per clock has either doubled or quintupled, I'm not sure; and as gojdo pointed out, the main bottleneck for R600-based cards, texture management rate, has nearly tripled (although I'm not sure on the clock rate, for the core except shaders is it really %35? I thought it was just 800 or 900MHz); and counting double the memory bandwidth and memory amount, nearly everything you can imagine has at least doubled.

The performance has to be somewhere close to double 3870. If it's only 1.5x, HD4850's price of $220 doesn't make any sense at all against the $150 HD3870. To me, everything points to the direction that 4870 will at least be 1.7 or 1.8 times HD3870, and 4850 will be at least 1.4-1.5 times HD3870, which fits in the 3dmark Vantage performance scores we have heard (4850 being slightly faster than 9800GTX)

---

with the score vr-zone reported its far from being faster then a 9800gtx (P6700 vs P9000)...

Aha, I'm sorry? A 9800GTX gets a Performance score of 13.000 in Vantage??

Quote:

---

Originally Posted by Shintai

Shaders aint double, ROPs aint changed at all and so on and on.

---

Exactly. The 16 ROPs were a weakpoint of the 38x0 and 2900 cards, so the fact that they've not increased them yet again doesn't bode well in my eyes.

8800GT had 16
8800GTS had 20
8800GTX had 24
GTX 260 will have 28
GTX 280 will have 32

:(

Quote:

---

Originally Posted by annihilat0r

Aha, I'm sorry? A 9800GTX gets a Performance score of 13.000 in Vantage??

---

haha sorry, orb failed me... it showed sli results even i filterd for single cards...

Q6600 with 9800 gets ~5800.

Okiez.

For the ROP thing, I've heard the z-fill per clock has doubled or something. That will probably remove the fillrate bottleneck

GX 280 still due out this month?

How come ROPs (RBEs) were a weakpoint for R600/RV670?
And I don't think you can really compare nV's ROPs to ATi's RBEs...

I'm looking forward to the new GTX 280
Will be a worthy replacement for my 8800GTS
I just hope my Enermax Infinity 720W PSU is man enough for the task.
John

im 100% sure this is bull:banana::banana::banana::banana:. u wanna know why?.. how come the card preforms exactly the same in all games.. and why dosent the gt 280/260 preform the same in all.. a lil bit strange in my eyes and one moore thing.. inpossible that the bouth nvidia cards can preform the same in one game..

advertising is what i call it.. no test ;)

Quote:

---

Originally Posted by JameCa

im 100% sure this is bull:banana::banana::banana::banana:. u wanna know why?.. how come the card preforms exactly the same in all games.. and why dosent the gt 280/260 preform the same in all.. a lil bit strange in my eyes and one moore thing.. inpossible that the bouth nvidia cards can preform the same in one game..

advertising is what i call it.. no test ;)

---

CPU limited? Even tho NVidia says no such thing! :ROTF:

->JameCa, maybe you should think this through one more time? ;)
The refence card will allways be at score 1, since it's the refence. The FPS doesn't matter, it's the difference that matters, and what Nvidia showed.

looks like COD4, UT3, and Fear (all 3 highly optimized & well programmed games) show raw graphics computational power increase in the GTX 200's. The other games show this as well as Forceware & DX communication improvements.

Edit: And, whats up with COJ and WIC? Are they still cpu limited? LOL

what does a 3870x2 score in vantage with performance level? the 4850 hits 6466. that doesnt sound bad. source for score http://www.vr-zone.com/articles/Rade...sted/5829.html

remeber the test was done on premature drivers

ROPS were NOT the weak point of the RV670 series

It was texture filling. Look at these tests hoom at B3d did on a RV670 w/ 3dMark06: http://forum.beyond3d.com/showpost.p...postcount=2376

Quote:

---

Just for kicks & since I'm currently reading a good book, I have just done a quick bunch of 3Dmark06 runs on my 3870 with various AA/AF configs.
E6600 @stock, 3870 @stock, Cat 8.5

no AF/AA 9883
16* AF/8*AA 8098
8* AF/no AA 8552
16* AF/no AA 8164
no AF/4*AA 9456
no AF/8*AA 9449
no AF/24*AA 8903

This was just one run of each config & I have stuff open in the background so not by any means scientific but there seems to be a pretty clear pattern.

---

I don't know about you, but it's pretty clear that it's AF that hurts the 3870 performance. Look at those numbers - AA is actually incredibly efficient. 8 x AF scores worse than 24 x AA!

If they doubled the TMU's, the AF issue should be fixed.

This makes sense anyways since no reviewers ever turn on AA w/o AF - however, the conclusion that it was AA killing performance was wrong.

Quote:

---

Originally Posted by Hornet331

with the score vr-zone reported its far from being faster then a 9800gtx (P6700 vs P9000)...

---

No, it is far faster than a 9800GTX.

With a quad-core CPU + 8800GTS 512MB (same as 9800GTX) @ 785/1891/2160, I get 6131, and my graphics score is 5609. I'm not sure whether or not they were talking about the graphics score or the overall, but either way the HD 4850 (6466) scores much higher than a heavily oc'd 8800GTS 512MB.

ROP's are not a bottleneck for the architecture right now. RV670 has much more pixel performance than G92 with its higher clock rates, yet it does not perform better. AMD already has plenty of ROP performance, it doesn't need more.

In comparing the 16 ROPs of RV770 to the 32 ROPs of GT200, you must remember (1) that the two products are not competitors, and (2) that AMD runs at a much higher clock speed. A HD 4870 with 850MHz core has only 18% less ROP performance than a GTX 260 @ 575MHz, if the two architectures are equal clock for clock.

Quote:

---

Originally Posted by Shintai

CPU limited? Even tho NVidia says no such thing! :ROTF:

---

there is no such thing if you play on normal resulotions, and only use a single VGA

Quote:

---

Originally Posted by Shintai

CPU limited? Even tho NVidia says no such thing! :ROTF:

---

i dont think the cpu is the bottleneck ;)

Quote:

---

Originally Posted by zerazax

ROPS were NOT the weak point of the RV670 series

It was texture filling. Look at these tests hoom at B3d did on a RV670 w/ 3dMark06: http://forum.beyond3d.com/showpost.p...postcount=2376



I don't know about you, but it's pretty clear that it's AF that hurts the 3870 performance. Look at those numbers - AA is actually incredibly efficient. 8 x AF scores worse than 24 x AA!

If they doubled the TMU's, the AF issue should be fixed.

This makes sense anyways since no reviewers ever turn on AA w/o AF - however, the conclusion that it was AA killing performance was wrong.

---

I saw that as well and agree that most of the "AA kills ATI" stuff is because reviewers always enable AA with AF; and it's in most cases AF killing ATI, not AA. But still, ATI's AA implementation isn't efficient in a lot of games (for example Crysis and DX10 Bioshock - AFAIK any form of AA nearly halves the performance).

Anyway, that post proves that ATI's bottleneck is really the texture units, which should have been overcome by now.

Now to think about it, I doubt NVidia has any answer to give to AMD in the $200-350 range. G92b? I doubt it'll hit 900MHz or something which will put it in a competition with the 4870.

If AMD dominates the 200-350 range, they dominate half of the market. And NVidia will sit around like ducks with its $700 cards.